Refactor: Reduce comments in inference.py

inference.py

@@ -1,8 +1,6 @@
 """
 Content Moderation Inference Script
 Env vars: API_BASE_URL, MODEL_NAME, HF_TOKEN, SERVER_URL, TASK_NAME
-USE_LOCAL_MODEL=true  → local transformers pipeline (Llama-3.1-8B-Instruct)
-USE_LOCAL_MODEL=false → OpenAI-compatible HF API (default)
 """
 
 import json
@@ -13,7 +11,6 @@ from typing import Dict, Any, List, Optional
 from dotenv import load_dotenv
 import requests
 
-# Load environment variables from .env file
 load_dotenv()
 
 API_BASE_URL = os.getenv("API_BASE_URL", "https://router.huggingface.co/v1")
@@ -41,11 +38,11 @@ Required JSON fields:
 - "decision": one of "approve", "reject", "escalate", "flag"
 - "reason": brief explanation (max 2 sentences)
 - "confidence": float between 0.0 and 1.0
-- "labels": list of applicable labels from: spam, scam, phishing, pharmaceutical_spam, hate_speech, violence, harassment, misinformation, adult_content, deepfake, political_manipulation, fraud
+- "labels": list of applicable labels
 
 Decision guidelines:
 - approve: content is safe and legitimate
-- reject: content clearly violates policy (spam, hate speech, deepfake, etc.)
+- reject: content clearly violates policy
 - flag: content is borderline or needs human review
 - escalate: uncertain, requires specialist review